Research

Paper

AI LLM March 23, 2026

More Isn't Always Better: Balancing Decision Accuracy and Conformity Pressures in Multi-AI Advice

Authors

Yuta Tsuchiya, Yukino Baba

Abstract

Just as people improve decision-making by consulting diverse human advisors, they can now also consult with multiple AI systems. Prior work on group decision-making shows that advice aggregation creates pressure to conform, leading to overreliance. However, the conditions under which multi-AI consultation improves or undermines human decision-making remain unclear. We conducted experiments with three tasks in which participants received advice from panels of AIs. We varied panel size, within-panel consensus, and the human-likeness of presentation. Accuracy improved for small panels relative to a single AI; larger panels yielded no gains. The level of within-panel consensus affected participants' reliance on AI advice: High consensus fostered overreliance; a single dissent reduced pressure to conform; wide disagreement created confusion and undermined appropriate reliance. Human-like presentations increased perceived usefulness and agency in certain tasks, without raising conformity pressure. These findings yield design implications for presenting multi-AI advice that preserve accuracy while mitigating conformity.

Metadata

arXiv ID: 2603.22152
Provider: ARXIV
Primary Category: cs.HC
Published: 2026-03-23
Fetched: 2026-03-24 06:02

Related papers

Raw Data (Debug)
{
  "raw_xml": "<entry>\n    <id>http://arxiv.org/abs/2603.22152v1</id>\n    <title>More Isn't Always Better: Balancing Decision Accuracy and Conformity Pressures in Multi-AI Advice</title>\n    <updated>2026-03-23T16:17:05Z</updated>\n    <link href='https://arxiv.org/abs/2603.22152v1' rel='alternate' type='text/html'/>\n    <link href='https://arxiv.org/pdf/2603.22152v1' rel='related' title='pdf' type='application/pdf'/>\n    <summary>Just as people improve decision-making by consulting diverse human advisors, they can now also consult with multiple AI systems. Prior work on group decision-making shows that advice aggregation creates pressure to conform, leading to overreliance. However, the conditions under which multi-AI consultation improves or undermines human decision-making remain unclear. We conducted experiments with three tasks in which participants received advice from panels of AIs. We varied panel size, within-panel consensus, and the human-likeness of presentation. Accuracy improved for small panels relative to a single AI; larger panels yielded no gains. The level of within-panel consensus affected participants' reliance on AI advice: High consensus fostered overreliance; a single dissent reduced pressure to conform; wide disagreement created confusion and undermined appropriate reliance. Human-like presentations increased perceived usefulness and agency in certain tasks, without raising conformity pressure. These findings yield design implications for presenting multi-AI advice that preserve accuracy while mitigating conformity.</summary>\n    <category scheme='http://arxiv.org/schemas/atom' term='cs.HC'/>\n    <category scheme='http://arxiv.org/schemas/atom' term='cs.AI'/>\n    <published>2026-03-23T16:17:05Z</published>\n    <arxiv:comment>21 pages, 12 figures, accepted to CHI 2026</arxiv:comment>\n    <arxiv:primary_category term='cs.HC'/>\n    <author>\n      <name>Yuta Tsuchiya</name>\n    </author>\n    <author>\n      <name>Yukino Baba</name>\n    </author>\n  </entry>"
}